Simplify project setup and add script entry point Replace the manual uv pip compile + uv pip sync + wheel-build sequence in build-gerrit.sh with a single `uv sync --extra dev`, which is the native uv project workflow. The build script now checks for uv on the host PATH before falling back to installing it via pip. Add [build-system] to pyproject.toml and commit uv.lock for reproducible installs. Drop the generated requirements.txt and uv-requirements.txt. Remove test.sh — `uv run pytest` covers everything it did (venv setup, env vars, test discovery) without a wrapper script. Add a `gerrit-mcp-server` console script entry point that delegates to cli_main, so the server can be run directly after installation. Use the script in the gemini config files and document uvx usage in the README and Gemini CLI setup guide. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> Change-Id: Ia9795e9c4f2a6d9b440c4c035155454616c75529
An MCP (Model Context Protocol) server for interacting with the Gerrit code review system. This server allows a language model like Gemini to query changes, retrieve details, and manage reviews by executing curl commands against the Gerrit REST API.
This server can be run as a persistent HTTP server or on-demand via STDIO.
For detailed information, please see the documents in the docs/ directory:
gerrit_config.json file and all authentication methods.Before you begin, ensure you have the following tools installed and available in your system's PATH.
pip if absent.Run the build script from the root of the gerrit-mcp-server project directory. This will create a virtual environment in .venv via uv sync and install all dependencies.
./build-gerrit.sh
You will need to create a gerrit_config.json file inside the gerrit_mcp_server directory. Copy the provided sample file gerrit_mcp_server/gerrit_config.sample.json and customize it for your environment. See the Configuration Guide for details on all available options.
cp gerrit_mcp_server/gerrit_config.sample.json gerrit_mcp_server/gerrit_config.json
To run the server as a persistent background process, use the server.sh script:
./server.sh start
./server.sh status
./server.sh stop
For on-demand STDIO mode, please see the Gemini CLI Setup Guide.
This is not an officially supported Google product. This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.